Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    may make or try

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     winter
    0.94
     vinter
    0.93
     anual
    0.85
    冬
    0.78
     constexpr
    0.77
     weekend
    0.77
     zomer
    0.77
     summer
    0.77
    jaar
    0.76
     winters
    0.76
    POSITIVE LOGITS
     verbally
    1.05
     gesturing
    0.94
     intermittently
    0.88
     interruptions
    0.88
     applauded
    0.87
     applause
    0.87
     cues
    0.83
     shouted
    0.83
     interrupting
    0.82
    ताली
    0.81
    Act Density 0.473%

    No Known Activations